From 726328d92a42b6d4b76078e2659f43067f82c4e8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 May 2016 10:35:03 +0200 Subject: locking/spinlock, arch: Update and fix spin_unlock_wait() implementations This patch updates/fixes all spin_unlock_wait() implementations. The update is in semantics; where it previously was only a control dependency, we now upgrade to a full load-acquire to match the store-release from the spin_unlock() we waited on. This ensures that when spin_unlock_wait() returns, we're guaranteed to observe the full critical section we waited on. This fixes a number of spin_unlock_wait() users that (not unreasonably) rely on this. I also fixed a number of ticket lock versions to only wait on the current lock holder, instead of for a full unlock, as this is sufficient. Furthermore; again for ticket locks; I added an smp_rmb() in between the initial ticket load and the spin loop testing the current value because I could not convince myself the address dependency is sufficient, esp. if the loads are of different sizes. I'm more than happy to remove this smp_rmb() again if people are certain the address dependency does indeed work as expected. Note: PPC32 will be fixed independently Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: chris@zankel.net Cc: cmetcalf@mellanox.com Cc: davem@davemloft.net Cc: dhowells@redhat.com Cc: james.hogan@imgtec.com Cc: jejb@parisc-linux.org Cc: linux@armlinux.org.uk Cc: mpe@ellerman.id.au Cc: ralf@linux-mips.org Cc: realmz6@gmail.com Cc: rkuo@codeaurora.org Cc: rth@twiddle.net Cc: schwidefsky@de.ibm.com Cc: tony.luck@intel.com Cc: vgupta@synopsys.com Cc: ysato@users.sourceforge.jp Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/mips/include/asm/spinlock.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'arch/mips') diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 40196bebe849..f485afe51514 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -12,6 +12,7 @@ #include #include +#include #include #include @@ -48,8 +49,22 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock) } #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(x) \ - while (arch_spin_is_locked(x)) { cpu_relax(); } + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + u16 owner = READ_ONCE(lock->h.serving_now); + smp_rmb(); + for (;;) { + arch_spinlock_t tmp = READ_ONCE(*lock); + + if (tmp.h.serving_now == tmp.h.ticket || + tmp.h.serving_now != owner) + break; + + cpu_relax(); + } + smp_acquire__after_ctrl_dep(); +} static inline int arch_spin_is_contended(arch_spinlock_t *lock) { -- cgit v1.2.3 From 4edac529eb629ccd598e2236c61762537f16e883 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 01:16:06 +0200 Subject: locking/atomic, arch/mips: Implement atomic{,64}_fetch_{add,sub,and,or,xor}() Implement FETCH-OP atomic primitives, these are very similar to the existing OP-RETURN primitives we already have, except they return the value of the atomic variable _before_ modification. This is especially useful for irreversible operations -- such as bitops (because it becomes impossible to reconstruct the state prior to modification). Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Signed-off-by: Ingo Molnar --- arch/mips/include/asm/atomic.h | 138 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 129 insertions(+), 9 deletions(-) (limited to 'arch/mips') diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 835b402e4574..431079f8e483 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -66,7 +66,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v) \ " " #asm_op " %0, %2 \n" \ " sc %0, %1 \n" \ " .set mips0 \n" \ - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ : "Ir" (i)); \ } while (unlikely(!temp)); \ } else { \ @@ -130,18 +130,78 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v) \ return result; \ } +#define ATOMIC_FETCH_OP(op, c_op, asm_op) \ +static __inline__ int atomic_fetch_##op(int i, atomic_t * v) \ +{ \ + int result; \ + \ + smp_mb__before_llsc(); \ + \ + if (kernel_uses_llsc && R10000_LLSC_WAR) { \ + int temp; \ + \ + __asm__ __volatile__( \ + " .set arch=r4000 \n" \ + "1: ll %1, %2 # atomic_fetch_" #op " \n" \ + " " #asm_op " %0, %1, %3 \n" \ + " sc %0, %2 \n" \ + " beqzl %0, 1b \n" \ + " move %0, %1 \n" \ + " .set mips0 \n" \ + : "=&r" (result), "=&r" (temp), \ + "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i)); \ + } else if (kernel_uses_llsc) { \ + int temp; \ + \ + do { \ + __asm__ __volatile__( \ + " .set "MIPS_ISA_LEVEL" \n" \ + " ll %1, %2 # atomic_fetch_" #op " \n" \ + " " #asm_op " %0, %1, %3 \n" \ + " sc %0, %2 \n" \ + " .set mips0 \n" \ + : "=&r" (result), "=&r" (temp), \ + "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i)); \ + } while (unlikely(!result)); \ + \ + result = temp; \ + } else { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + result = v->counter; \ + v->counter c_op i; \ + raw_local_irq_restore(flags); \ + } \ + \ + smp_llsc_mb(); \ + \ + return result; \ +} + #define ATOMIC_OPS(op, c_op, asm_op) \ ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_OP_RETURN(op, c_op, asm_op) + ATOMIC_OP_RETURN(op, c_op, asm_op) \ + ATOMIC_FETCH_OP(op, c_op, asm_op) ATOMIC_OPS(add, +=, addu) ATOMIC_OPS(sub, -=, subu) -ATOMIC_OP(and, &=, and) -ATOMIC_OP(or, |=, or) -ATOMIC_OP(xor, ^=, xor) +#undef ATOMIC_OPS +#define ATOMIC_OPS(op, c_op, asm_op) \ + ATOMIC_OP(op, c_op, asm_op) \ + ATOMIC_FETCH_OP(op, c_op, asm_op) + +#define atomic_fetch_or atomic_fetch_or + +ATOMIC_OPS(and, &=, and) +ATOMIC_OPS(or, |=, or) +ATOMIC_OPS(xor, ^=, xor) #undef ATOMIC_OPS +#undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP @@ -414,17 +474,77 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v) \ return result; \ } +#define ATOMIC64_FETCH_OP(op, c_op, asm_op) \ +static __inline__ long atomic64_fetch_##op(long i, atomic64_t * v) \ +{ \ + long result; \ + \ + smp_mb__before_llsc(); \ + \ + if (kernel_uses_llsc && R10000_LLSC_WAR) { \ + long temp; \ + \ + __asm__ __volatile__( \ + " .set arch=r4000 \n" \ + "1: lld %1, %2 # atomic64_fetch_" #op "\n" \ + " " #asm_op " %0, %1, %3 \n" \ + " scd %0, %2 \n" \ + " beqzl %0, 1b \n" \ + " move %0, %1 \n" \ + " .set mips0 \n" \ + : "=&r" (result), "=&r" (temp), \ + "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i)); \ + } else if (kernel_uses_llsc) { \ + long temp; \ + \ + do { \ + __asm__ __volatile__( \ + " .set "MIPS_ISA_LEVEL" \n" \ + " lld %1, %2 # atomic64_fetch_" #op "\n" \ + " " #asm_op " %0, %1, %3 \n" \ + " scd %0, %2 \n" \ + " .set mips0 \n" \ + : "=&r" (result), "=&r" (temp), \ + "=" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter) \ + : "memory"); \ + } while (unlikely(!result)); \ + \ + result = temp; \ + } else { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + result = v->counter; \ + v->counter c_op i; \ + raw_local_irq_restore(flags); \ + } \ + \ + smp_llsc_mb(); \ + \ + return result; \ +} + #define ATOMIC64_OPS(op, c_op, asm_op) \ ATOMIC64_OP(op, c_op, asm_op) \ - ATOMIC64_OP_RETURN(op, c_op, asm_op) + ATOMIC64_OP_RETURN(op, c_op, asm_op) \ + ATOMIC64_FETCH_OP(op, c_op, asm_op) ATOMIC64_OPS(add, +=, daddu) ATOMIC64_OPS(sub, -=, dsubu) -ATOMIC64_OP(and, &=, and) -ATOMIC64_OP(or, |=, or) -ATOMIC64_OP(xor, ^=, xor) #undef ATOMIC64_OPS +#define ATOMIC64_OPS(op, c_op, asm_op) \ + ATOMIC64_OP(op, c_op, asm_op) \ + ATOMIC64_FETCH_OP(op, c_op, asm_op) + +ATOMIC64_OPS(and, &=, and) +ATOMIC64_OPS(or, |=, or) +ATOMIC64_OPS(xor, ^=, xor) + +#undef ATOMIC64_OPS +#undef ATOMIC64_FETCH_OP #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP -- cgit v1.2.3 From b53d6bedbe781974097fd8c38263f6cc78ff9ea7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 00:58:25 +0200 Subject: locking/atomic: Remove linux/atomic.h:atomic_fetch_or() Since all architectures have this implemented now natively, remove this dead code. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/mips/include/asm/atomic.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/mips') diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 431079f8e483..387ce288334e 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -194,8 +194,6 @@ ATOMIC_OPS(sub, -=, subu) ATOMIC_OP(op, c_op, asm_op) \ ATOMIC_FETCH_OP(op, c_op, asm_op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, &=, and) ATOMIC_OPS(or, |=, or) ATOMIC_OPS(xor, ^=, xor) -- cgit v1.2.3 From 4ec45856b698c37e73d973fb4b1a094dfb9d5732 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 01:15:25 +0200 Subject: locking/atomic, arch/mips: Convert to _relaxed atomics Generic code will construct {,_acquire,_release} versions by adding the required smp_mb__{before,after}_atomic() calls. XXX if/when MIPS will start using their new SYNCxx instructions they can provide custom __atomic_op_{acquire,release}() macros as per the powerpc example. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Signed-off-by: Ingo Molnar --- arch/mips/include/asm/atomic.h | 42 ++++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 20 deletions(-) (limited to 'arch/mips') diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 387ce288334e..0ab176bdb8e8 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -79,12 +79,10 @@ static __inline__ void atomic_##op(int i, atomic_t * v) \ } #define ATOMIC_OP_RETURN(op, c_op, asm_op) \ -static __inline__ int atomic_##op##_return(int i, atomic_t * v) \ +static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v) \ { \ int result; \ \ - smp_mb__before_llsc(); \ - \ if (kernel_uses_llsc && R10000_LLSC_WAR) { \ int temp; \ \ @@ -125,18 +123,14 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v) \ raw_local_irq_restore(flags); \ } \ \ - smp_llsc_mb(); \ - \ return result; \ } #define ATOMIC_FETCH_OP(op, c_op, asm_op) \ -static __inline__ int atomic_fetch_##op(int i, atomic_t * v) \ +static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v) \ { \ int result; \ \ - smp_mb__before_llsc(); \ - \ if (kernel_uses_llsc && R10000_LLSC_WAR) { \ int temp; \ \ @@ -176,8 +170,6 @@ static __inline__ int atomic_fetch_##op(int i, atomic_t * v) \ raw_local_irq_restore(flags); \ } \ \ - smp_llsc_mb(); \ - \ return result; \ } @@ -189,6 +181,11 @@ static __inline__ int atomic_fetch_##op(int i, atomic_t * v) \ ATOMIC_OPS(add, +=, addu) ATOMIC_OPS(sub, -=, subu) +#define atomic_add_return_relaxed atomic_add_return_relaxed +#define atomic_sub_return_relaxed atomic_sub_return_relaxed +#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed +#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed + #undef ATOMIC_OPS #define ATOMIC_OPS(op, c_op, asm_op) \ ATOMIC_OP(op, c_op, asm_op) \ @@ -198,6 +195,10 @@ ATOMIC_OPS(and, &=, and) ATOMIC_OPS(or, |=, or) ATOMIC_OPS(xor, ^=, xor) +#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed +#define atomic_fetch_or_relaxed atomic_fetch_or_relaxed +#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed + #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN @@ -420,12 +421,10 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v) \ } #define ATOMIC64_OP_RETURN(op, c_op, asm_op) \ -static __inline__ long atomic64_##op##_return(long i, atomic64_t * v) \ +static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \ { \ long result; \ \ - smp_mb__before_llsc(); \ - \ if (kernel_uses_llsc && R10000_LLSC_WAR) { \ long temp; \ \ @@ -467,18 +466,14 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v) \ raw_local_irq_restore(flags); \ } \ \ - smp_llsc_mb(); \ - \ return result; \ } #define ATOMIC64_FETCH_OP(op, c_op, asm_op) \ -static __inline__ long atomic64_fetch_##op(long i, atomic64_t * v) \ +static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v) \ { \ long result; \ \ - smp_mb__before_llsc(); \ - \ if (kernel_uses_llsc && R10000_LLSC_WAR) { \ long temp; \ \ @@ -519,8 +514,6 @@ static __inline__ long atomic64_fetch_##op(long i, atomic64_t * v) \ raw_local_irq_restore(flags); \ } \ \ - smp_llsc_mb(); \ - \ return result; \ } @@ -532,6 +525,11 @@ static __inline__ long atomic64_fetch_##op(long i, atomic64_t * v) \ ATOMIC64_OPS(add, +=, daddu) ATOMIC64_OPS(sub, -=, dsubu) +#define atomic64_add_return_relaxed atomic64_add_return_relaxed +#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed +#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed +#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed + #undef ATOMIC64_OPS #define ATOMIC64_OPS(op, c_op, asm_op) \ ATOMIC64_OP(op, c_op, asm_op) \ @@ -541,6 +539,10 @@ ATOMIC64_OPS(and, &=, and) ATOMIC64_OPS(or, |=, or) ATOMIC64_OPS(xor, ^=, xor) +#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed +#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed +#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed + #undef ATOMIC64_OPS #undef ATOMIC64_FETCH_OP #undef ATOMIC64_OP_RETURN -- cgit v1.2.3